1 /*
2 * Copyright (c) 2006, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package com.sun.xml.internal.stream.writers;
27
28 import java.io.Writer;
29 import java.io.OutputStream;
30 import java.io.IOException;
31
32 import com.sun.org.apache.xerces.internal.util.XMLChar;
33
34 /**
35 * <p>This class is used to write a stream of chars as a stream of
36 * bytes using the UTF8 encoding. It assumes that the underlying
37 * output stream is buffered or does not need additional buffering.</p>
38 *
39 * <p>It is more efficient than using a <code>java.io.OutputStreamWriter</code>
40 * because it does not need to be wrapped in a
41 * <code>java.io.BufferedWriter</code>. Creating multiple instances
42 * of <code>java.io.BufferedWriter</code> has been shown to be very
43 * expensive in JAX-WS.</p>
44 *
45 * @author Santiago PericasGeertsen
46 */
47 public final class UTF8OutputStreamWriter extends Writer {
48
49 /**
50 * Undelying output stream. This class assumes that this
51 * output stream does not need buffering.
52 */
53 OutputStream out;
54
55 /**
56 * Java represents chars that are not in the Basic Multilingual
57 * Plane (BMP) in UTF-16. This int stores the first code unit
58 * for a code point encoded in two UTF-16 code units.
59 */
60 int lastUTF16CodePoint = 0;
61
62 public UTF8OutputStreamWriter(OutputStream out) {
63 this.out = out;
64 }
65
66 public String getEncoding() {
67 return "UTF-8";
68 }
69
70 public void write(int c) throws IOException {
71 // Check in we are encoding at high and low surrogates
72 if (lastUTF16CodePoint != 0) {
73 final int uc =
74 (((lastUTF16CodePoint & 0x3ff) << 10) | (c & 0x3ff)) + 0x10000;
75
76 if (uc < 0 || uc >= 0x200000) {
77 throw new IOException("Atttempting to write invalid Unicode code point '" + uc + "'");
78 }
79
80 out.write(0xF0 | (uc >> 18));
81 out.write(0x80 | ((uc >> 12) & 0x3F));
82 out.write(0x80 | ((uc >> 6) & 0x3F));
83 out.write(0x80 | (uc & 0x3F));
84
85 lastUTF16CodePoint = 0;
86 return;
87 }
88
89 // Otherwise, encode char as defined in UTF-8
90 if (c < 0x80) {
91 // 1 byte, 7 bits
92 out.write(c);
93 }
94 else if (c < 0x800) {
95 // 2 bytes, 11 bits
96 out.write(0xC0 | (c >> 6)); // first 5
97 out.write(0x80 | (c & 0x3F)); // second 6
98 }
99 else if (c <= '\uFFFF') {
100 if (!XMLChar.isHighSurrogate(c) && !XMLChar.isLowSurrogate(c)) {
101 // 3 bytes, 16 bits
102 out.write(0xE0 | (c >> 12)); // first 4
103 out.write(0x80 | ((c >> 6) & 0x3F)); // second 6
104 out.write(0x80 | (c & 0x3F)); // third 6
105 }
106 else {
107 lastUTF16CodePoint = c;
108 }
109 }
110 }
111
112 public void write(char cbuf[]) throws IOException {
113 for (int i = 0; i < cbuf.length; i++) {
114 write(cbuf[i]);
115 }
116 }
117
118 public void write(char cbuf[], int off, int len) throws IOException {
119 for (int i = 0; i < len; i++) {
120 write(cbuf[off + i]);
121 }
122 }
123
124 public void write(String str) throws IOException {
125 final int len = str.length();
126 for (int i = 0; i < len; i++) {
127 write(str.charAt(i));
128 }
129 }
130
131 public void write(String str, int off, int len) throws IOException {
132 for (int i = 0; i < len; i++) {
133 write(str.charAt(off + i));
134 }
135 }
136
137 public void flush() throws IOException {
138 out.flush();
139 }
140
141 public void close() throws IOException {
142 if (lastUTF16CodePoint != 0) {
143 throw new IllegalStateException("Attempting to close a UTF8OutputStreamWriter"
144 + " while awaiting for a UTF-16 code unit");
145 }
146 out.close();
147 }
148
149 }